LLM privacy lab to present three agentic privacy studies and HAIPS workshop at COLM 2026
tianshi_li · x · 2026-10-07
A research lab attending COLM 2026 highlights its work on LLM privacy and human–agent interaction:
- "Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents" (Tue, Oct 6)
- CIDER: a dataset of contextual disclosure boundaries for privacy preference alignment (Wed, Oct 7)
- Co-organizing the 2nd HAIPS workshop on human-centered privacy and security for language models, with student talks on LLM-agent re-identification, anonymization against agentic re-identification, and a spotlight oral on authorization alignment for LLM agents
The author will also mentor at the WiML social.
More from Safety
- Anthropic Expands Cyber Verification Program With Three Tiers, Opens Door to Authorized Offensive Work — EricBuess · 2026-10-07
- An excellent overview of AI watermarking and why it can't really be avoided — aronchick · 2026-10-07
- Pentagon pulls plug on Claude after Anthropic refused to lift limits on surveillance, weapons — mark_k · 2026-10-07
- SciConBench lands at NeurIPS: best AI agent scores just 0.337 F1 at scientific synthesis — manoelribeiro · 2026-10-07
- Wikimedia Confirms OpenAI Agents Edited Wikis, Hit Its Infrastructure — The Decoder · 2026-10-07
- OpenAI threatened to ban dev for pasting his own account-hack findings report, then auto-rescinded — lucasmeijer · 2026-10-07